Gain insights into advanced deep learning and NLP by building 12 real-world projects using tools like TensorFlow and scikit-learn. Enhance your portfolio with industry-relevant skills.

dockerfile.tar.gz

python3

spa-job

In this course, you'll not only learn advanced deep learning concepts, but you'll also practice building some advanced deep learning and Natural Language Processing (NLP) projects. By the end, you will be able to utilize deep learning algorithms that are used at large in industry.

 

This is a project-based course with 12 projects in total. This will get you used to building real-world applications that are being used in a wide range of industries. You will be exposed to the most common tools used for machine learning projects including: NumPy, Matplotlib, scikit-learn, Tensorflow, and more.

 

It’s recommended that you have a firm grasp in these topic areas: Python basics, Numpy and Pandas, and Artificial Neural Networks.

 

Once you’re finished, you will have the experience to start building your own amazing projects, and some great new additions to your portfolio.

Building Advanced Deep Learning and NLP Projects

You might be thinking that transfer learning is a pretty cool technique, but why do we need to use it in computer vision or in any other ML methods. So, here's your answer!

## Why do we need transfer learning?
Let's look at an example.

Suppose you want to build an image classifier, and you have a dataset that contains around 2000 images. If you wish that your model could learn complex features, and you want to train a complex model with many convolutional layers, then you might end up in training around 10 million parameters.

Now, if you know about neural networks, then the above architecture of your model will eventually overfit in just one or two `epochs`. There will be no generalization in your model, and eventually, the model's results will be very poor.

## How to solve the above problem?
This is where `Transfer Learning` comes. The idea behind transfer learning is to use a pre-trained network.

Some very famous Pre-Trained Networks are -
1. Alexnet
2. VGG19
3. VGG16
4. MobileNet
5. ResNet

To build our Pokemon classifier we will be using the **ResNet50** model.

As an assignment, you will be building up a classifier using the **MobileNet** model.

___

# Why do we need transfer learning?
Let's look at an example.

Suppose you want to build an image classifier, and you have a dataset that contains around 2000 images. If you wish that your model could learn complex features, and you want to train a complex model with many convolutional layers, then you might end up in training around 10 million parameters.

Now, if you know about neural networks, then the above architecture of your model will eventually overfit in just one or two `epochs`. There will be no generalization in your model, and eventually, the model's results will be very poor.

# How to solve the above problem?
This is where `Transfer Learning` comes. The idea behind transfer learning is to use a pre-trained network.

Some very famous Pre-Trained Networks are -
1. Alexnet
2. VGG19
3. VGG16
4. MobileNet
5. ResNet

To build our Pokemon classifier we will be using the **ResNet50** model.

As an assignment, you will be building up a classifier using the **MobileNet** model.

___

In this lesson, we will discuss why transfer learning is required.

Welcome to the Course

Project: Build a COVID-19 Detection System Using X-Rays

Project: Building a Pokemon Classifier Using Transfer Learning

Project: Text Generation Using Markov Chains

Word Embedding: Two Mini Projects

Project: IMDB Reviews Sentiment Analysis

Project: Deciphering Text Using Character-Level RNNs

Project: Emoji Predictor Using Transfer Learning in NLP

Final Exam

Where to Go Next?

Transfer Learning in Vision

Why do we need transfer learning?